# Gauge CLI > Gauge CLI runs real coding agents (Claude Code, Codex, Pi, OpenCode) against your skills, CLIs, SDKs, MCP servers and docs in Docker, records where they get stuck, and lets your agent test fixes before release. - Canonical: https://www.anchorterminal.com/tools/gauge-cli - Pricing: https://www.anchorterminal.com/tools/gauge-cli#pricing - Reviews: https://www.anchorterminal.com/tools/gauge-cli#reviews - Markdown: https://www.anchorterminal.com/tools/gauge-cli.md (~4,550 tokens) - Slim: https://www.anchorterminal.com/tools/gauge-cli.min.md (~1,130 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/gauge-cli.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key) - DNS: dig +short TXT gauge-cli.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.. and .vs.. under the zone, and the same under grade.letme.dev) - Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data) - Updated: 2026-11-06 ## Overview **Grade C · 60.4/100 · rank #590 of 1354 · #13 in Agent observability & evals · not agent-ready · confidence low** ## Assessment An open-source CLI that measures how coding agents get on with your product and checks fixes before you ship them, locally in Docker with no account. It's young and pre-1.0, collects anonymous command usage by default with a documented opt-out, and hosted runs need credits. ## Facts | Field | Value | | --- | --- | | Vendor | Gauge (https://www.withgauge.com/agents/) | | Kind | cli | | Category | Agent observability & evals (https://www.anchorterminal.com/categories/agent-observability) | | Auth | None · Local mode needs no Gauge account, only credentials for the agent under test (native Claude or Codex logins, or API keys). Hosted Gauge uses `gauge auth login`, with a device flow for remote terminals. | | Pricing | Freemium (Freemium) · The CLI and local mode are free and MIT-licensed; agent usage is billed by your provider or subscription. Hosted Gauge runs on workspace credits, whose prices weren't read (checked 2026-11-06). | | x402 | No · No payment protocol in the CLI or its README; hosted runs use workspace credits (checked 2026-11-06). | | Licence | MIT | | Packages | npm: `@withgauge/cli` | | Source | https://github.com/gauge-sh/gauge-cli | | Docs | https://docs.withgauge.com/agents | | llms.txt | not found | | Last release | 2026-11-04 | | Surface graded | The open-source CLI, read from a clone of github.com/gauge-sh/gauge-cli on 6 November 2026: the README, cli/README.md, cli/package.json, the changelog, workflows and tags. Hosted Gauge's pages and pricing weren't read. Nothing was installed or run | | Local and hosted | Local runs use Docker and your agent credentials, with results in a private SQLite database that your coding agent analyses. Hosted Gauge adds managed compute, automated judging, native binaries, website previews, authenticated MCP servers and APIs, scheduled measurements and GitHub PR checks, on workspace credits | | Releases | CLI 0.23.0 (20 October), 0.24.0 (22 October), 0.25.0 and 0.25.1 (27 October), 0.26.0 (28 October), 0.27.0 (2 November) and 0.28.0 (4 November) 2026, plus runtime, gateway and adapter packages | | Telemetry | On by default for the installed CLI: command name, timestamp, CLI version and a random installation ID, excluding arguments, prompts, file contents and account identifiers. Off with gauge telemetry disable or GAUGE_TELEMETRY_DISABLED=1 | | Capabilities | obs.evals | | Tags | open-source, mit, cli, node, docker, telemetry, new | | JSON | https://www.anchorterminal.com/api/v1/tools/gauge-cli.json | ## Score breakdown (methodology v0.7, October 2026 research run) Assessed 2026-11-06 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: low. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 60 | 12.0 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 60 | 9.8 | | Agent ergonomics | 13% | 16.2 | 75 | 12.2 | | Security & auth | 14% | 17.5 | 55 | 9.6 | | Payments & pricing | 10% | 12.5 | 40 | 5.0 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 82 | 7.2 | | Transparency & trust (editorial 78, provenance 27) | 7% | 8.8 | 53 | 4.6 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **60.4 → C** | ### Why each score - Reliability 60 (checked 2026-11-06): Local package. Installs from npm as @withgauge/cli with Node 22.13 or later and Docker stated (20). checks.yml runs npm run check on push and pull request across a matrix, and the repository has 76 test files; whether main passes wasn't read (20 of 25). Issues weren't read (5, unchecked). A dated changelog with Added sections per release (15). Version 0.28.0 (0). 20 + 20 + 5 + 15 + 0 = 60. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 60 (checked 2026-11-06): CLI reading. No machine-readable contract, -o json on read commands (10 of 25). No llms.txt; instructions bundled in the CLI for agents (5). The README says what it finds and when local or hosted fits (16 of 20). Commands with help text; typed flags (9 of 15). Worked examples, no error reference (8 of 15). Dated changelog and semver tags (12 of 15). 10 + 5 + 16 + 9 + 8 + 12 = 60. - Agent ergonomics 75 (checked 2026-11-06): CLI reading for an agent driving it. Bundled instructions match the installed version, and output is filterable with -o json (20 of 25). Run summaries and Findings with queryable fields (15 of 20). Errors not documented as a reference (10 of 20). Reruns from checkpoints and a recheck command with a confirm step (15 of 20). Four commands to start, Node only (15 of 15). 20 + 15 + 10 + 15 + 15 = 75. - Security & auth 55 (checked 2026-11-06): Local tool. Agent credentials stay on your machine in local mode; hosted login with a device flow (20 of 30). Test agents run in fresh Docker sessions with injected inputs, and the gateway brokers credentials in hosted mode (12 of 20). Agents under test read your product's docs and outputs, with no prompt-injection guidance (5 of 15). Local transcripts and SQLite evidence per run (10 of 15). No security policy found (8 of 20). 20 + 12 + 5 + 10 + 8 = 55. - Payments & pricing 40 (checked 2026-11-06): Scored on the hosted option. No payment protocol (0). Credit prices weren't found on the pages read (0). Local mode is free with no card (20). Local mode needs no sign-up (20). 0 + 0 + 20 + 20 = 40. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 82 (checked 2026-11-06): CLI 0.28.0 on 4 November 2026 (30). Six releases in 90 days (20). Issues and pull requests weren't read; a support address and issue tracker are published (12 of 25). Current official package (15). CI on push and pull request (5 of 10, results not read). 30 + 20 + 12 + 15 + 5 = 82. - Transparency & trust 53 (checked 2026-11-06): MIT (30). Local data stays in .gauge/ and telemetry fields are listed; hosted data handling wasn't read (18 of 30). Dated changelog, no deprecation policy (10 of 20). Telemetry on by default, disclosed with an opt-out (20). 30 + 18 + 10 + 20 = 78. Fix list, everything this grade says the listing lacks, the biggest gain first (13 items). What it covers is at https://www.anchorterminal.com/fixes/gauge-cli.md (JSON https://www.anchorterminal.com/fixes/gauge-cli.json). The whole list for a coding agent comes from `POST https://www.anchorterminal.com/api/v1/fix-list` with `{"listing": "gauge-cli", "plan": "read"}`, free while the beta runs ### What we couldn't check - Competitor note: Gauge runs agents against a product to find where they get stuck, close to Anchor Terminal's checks and audits. The listing-check rule names LocalGhost and letme for the competitor procedure, not the audits, so it was graded by one reader. The founder may want the competitor procedure and a disclosure - unchecked: hosted Gauge's pricing, terms, privacy and docs at docs.withgauge.com, and GitHub issues ### Sources - repository README, cli README, package.json, changelog, workflows and tags: (seen 2026-11-06) - changelog, 0.23.0 to 0.28.0: (seen 2026-11-06) - lead, Agent Tools Today for 5 November 2026: (seen 2026-11-06) ## Score history Every move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/gauge-cli/history.json - 2026-11-06: graded 60.4 C (methodology 0.7) ## Who's behind it (provenance 27/100, checked 2026-11-06) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | not found | 0/20 | | Domain age | withgauge.com, no registry record we could read | 0/15 | | Endpoint on the vendor's domain | no hosted endpoint | n/a | | Terms of service | nothing hosted, so the MIT licence stands in | 10/10 | | Privacy policy | nothing hosted, not scored | n/a | | Status page | not found | 0/10 | | Changelog | published | 10/10 | | security.txt | not found | 0/10 | | People named | not researched yet | n/a | | Support route | not researched yet | n/a | Not looked up: RDAP isn't requested under the 1 November 2026 rules. The npm package's author is Gauge , its homepage agents.withgauge.com, and its repository field points at gauge-sh/gauge-cli. The licence names Gauge. Hosted Gauge's terms and privacy weren't read, and security.txt wasn't checked. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full. **Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored. ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Strengths - Runs Claude Code, Codex, Pi and OpenCode in fresh Docker sessions against working-tree or pre-release versions - Local mode needs no Gauge account, only your existing agent credentials - Dated changelog with six releases in about two weeks - Instructions bundled in the CLI for coding agents, and -o json on read commands - CI runs checks on every push and pull request ## Weaknesses - Collects anonymous command usage by default, with an opt-out - Pre-1.0 and about two weeks old in this repository - Docs, authenticated MCP servers and authenticated APIs need hosted Gauge and credits - Hosted credit prices weren't found on the pages read ## Before you call it (notes for agents) 1. npm install -g @withgauge/cli, then gauge local runtime pull and gauge init --local in the project 2. Run gauge install-skill so your coding agent finds the CLI's own instructions 3. Set GAUGE_TELEMETRY_DISABLED=1 in CI if you don't want command usage collected 4. Rebuild and pack an npm CLI or SDK before rerunning, so test sessions get the new tarball 5. Keep .gauge/ private; it holds measurements and analyses ## Connect Install: ```bash npm install -g @withgauge/cli gauge local runtime pull gauge init --local gauge install-skill ``` ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Arize Phoenix | BB | 72.1 | 124 | obs.evals | no | https://www.anchorterminal.com/tools/arize-phoenix.md | | Respan API + MCP | BB | 72 | 128 | obs.evals | no | https://www.anchorterminal.com/tools/respan.md | | Langfuse API + MCP | BB | 71.8 | 132 | obs.evals | no | https://www.anchorterminal.com/tools/langfuse.md | | LangSmith API + MCP | BB | 71.6 | 137 | obs.evals | no | https://www.anchorterminal.com/tools/langsmith.md | | Opik API + MCP | BB | 71.5 | 138 | obs.evals | no | https://www.anchorterminal.com/tools/opik.md | | LangWatch | B | 65.6 | 373 | obs.evals | no | https://www.anchorterminal.com/tools/langwatch.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - Discussed on Hacker News on 5 November 2026. The repository's first commit is 20 October 2026, importing an existing CLI at 0.23.0 (source: ) - Finds problems such as interactive commands that block an agent, deprecated patterns an agent reaches for, and skills that go unused, then reruns cases against pre-release artifacts to check a fix (source: ) - Collects command usage by default (command name, timestamp, version and a random install ID, no arguments or prompts), disabled with `gauge telemetry disable` or GAUGE_TELEMETRY_DISABLED=1 (source: ) - Six CLI releases in October and November 2026, from 0.23.0 on 20 October to 0.28.0 on 4 November, each in a dated changelog (source: ) - #13 of 22 in Best agent tracing, monitoring and evaluation tools: https://www.anchorterminal.com/best/agent-observability/index.md - All 250 evals comparisons: https://www.anchorterminal.com/compare/agent-observability/index.md ## Compare - [Arize Phoenix vs Gauge CLI](https://www.anchorterminal.com/compare/arize-phoenix-vs-gauge-cli.md): BB 72.1 vs C 60.4 - [Baserun vs Gauge CLI](https://www.anchorterminal.com/compare/baserun-vs-gauge-cli.md): F 7.3 vs C 60.4 - [BotGauge vs Gauge CLI](https://www.anchorterminal.com/compare/botgauge-vs-gauge-cli.md): E 40.7 vs C 60.4 - [Braintrust API + MCP vs Gauge CLI](https://www.anchorterminal.com/compare/braintrust-vs-gauge-cli.md): B 65.1 vs C 60.4 - [DeepEval vs Gauge CLI](https://www.anchorterminal.com/compare/deepeval-vs-gauge-cli.md): C 61.9 vs C 60.4 - [Galileo API + MCP vs Gauge CLI](https://www.anchorterminal.com/compare/galileo-vs-gauge-cli.md): E 44.9 vs C 60.4 - [Gauge CLI vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-helicone.md): C 60.4 vs E 42.7 - [Gauge CLI vs HoneyHive](https://www.anchorterminal.com/compare/gauge-cli-vs-honeyhive.md): C 60.4 vs D 51.8 - [Gauge CLI vs Laminar API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-laminar.md): C 60.4 vs C 57 - [Gauge CLI vs Langfuse API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-langfuse.md): C 60.4 vs BB 71.8 - [Gauge CLI vs LangSmith API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-langsmith.md): C 60.4 vs BB 71.6 - [Gauge CLI vs LangWatch](https://www.anchorterminal.com/compare/gauge-cli-vs-langwatch.md): C 60.4 vs B 65.6 - [Gauge CLI vs MLflow Tracing](https://www.anchorterminal.com/compare/gauge-cli-vs-mlflow-tracing.md): C 60.4 vs D 51.5 - [Gauge CLI vs Opik API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-opik.md): C 60.4 vs BB 71.5 - [Gauge CLI vs Overmind](https://www.anchorterminal.com/compare/gauge-cli-vs-overmind.md): C 60.4 vs C 58.5 - [Gauge CLI vs Prefactor](https://www.anchorterminal.com/compare/gauge-cli-vs-prefactor.md): C 60.4 vs C 61.5 - [Gauge CLI vs Pydantic Logfire](https://www.anchorterminal.com/compare/gauge-cli-vs-pydantic-logfire.md): C 60.4 vs B 65.1 - [Gauge CLI vs Respan API + MCP](https://www.anchorterminal.com/compare/gauge-cli-vs-respan.md): C 60.4 vs BB 72 - [Gauge CLI vs W&B Weave](https://www.anchorterminal.com/compare/gauge-cli-vs-wandb-weave.md): C 60.4 vs B 63.5 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on withgauge.com or one of its subdomains, or the README at the root of github.com/gauge-sh/gauge-cli. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "gauge-cli", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Gauge CLI on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Gauge CLI on Anchor Terminal](https://www.anchorterminal.com/badges/gauge-cli.svg)](https://www.anchorterminal.com/tools/gauge-cli) ``` Plain link: ```html Gauge CLI on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Gauge CLI is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/gauge-cli-dark.png - Light: https://www.anchorterminal.com/assets/share/gauge-cli-light.png --- Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp